Method for adjusting a device behavior based on privacy classes

1. A method for adjusting behavior of a social robot with respect to a privacy class, comprising:

collecting, by the social robot, sensory inputs from a plurality of sensors, wherein the sensory inputs comprising user-related audio data recorded from a microphone, user-related image and video data received from a camera and user-related movements detected by a motion detector;

analyzing the sensory inputs by the social robot based on a privacy class of a plurality of privacy classes defined within the social robot, the privacy class comprising a category defining how the social robot interprets the sensory inputs in terms of a user's personal privacy in a social situation;

determining, by the social robot, a privacy rule, defined within the social robot, based on the privacy class and the a nalyzed sensory inputs, the determined privacy rule being indicative of actions that may be executed by the social robot to interact with the user; initiating an engagement of the social robot with the user based on the determined privacy rule;

wherein the plurality of privacy class includes various levels of privacy classes having various sensitivity levels; and

wherein initiating an engagement of the user is dependent on a determined sensitivity level.

2. The method of claim 1 , wherein the plurality of privacy classes is retrieved from a storage.

3. The method of claim 1 , wherein the sensory inputs are collected with respect to the user.

4. The method of claim 1 , wherein the sensory inputs are collected with respect to an entity located within a predetermined distance from the user.

5. The method of claim 4 , further comprising: analyzing the sensory inputs for classifying the at least an entity.

6. The method of claim 5 , further comprising:

analyzing the sensory inputs, the entity's classification, and the privacy rule.

7. The method of claim 1 , wherein the at least a privacy class is determined based on machine learning techniques.

8. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process for adjusting behavior of a social robot with respect to a privacy class, the process comprising:

collecting, by the social robot, sensory inputs from a plurality of sensors, wherein the sensory inputs comprising user-related audio data recorded from a microphone, user- related image and video data received from a camera and user-related movements detected by a motion detector;

analyzing the sensory inputs by the social robot based on a privacy class of a plurality of privacy classes defined within the social robot, the privacy class comprising a category defining how the social robot interprets the sensory inputs in terms of a user's personal privacy in a social situation;

determining, by the social robot, a privacy rule, defined within the social robot, based on the privacy class and the analyzed sensory inputs, the determined privacy rule being indicative of actions that may be executed by the social robot to interact with the user;

initiating an engagement of the social robot with the user based on the determined privacy rule;

wherein the plurality of privacy class includes various levels of privacy classes having various sensitivity levels; and

wherein initiating an engagement of the user is dependent on a determined sensitivity level.

9. A system for adjusting behavior of a social robot with respect to a privacy class, comprising:

a processing circuitry of the social robot; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

collecting sensory inputs from a plurality of sensors, wherein the sensory inputs comprising:

user-related audio data recorded from a microphone, user-related image and video data received from a camera and user-related movements detected by a motion detector;

analyzing the sensory inputs based on a privacy class of a plurality of privacy classes defined within the system, the privacy class comprising a category defining how the social robot interprets the sensory inputs in terms of a user's personal privacy in a social situation;

determining a privacy rule, defined within the system, based on the privacy class and the analyzed sensory inputs, the determined privacy rule being indicative of actions that may be executed by the social robot to interact with the user;

initiating an engagement of the social robot with the user based on the determined privacy rule;

wherein the plurality of privacy class includes various levels of privacy classes having various sensitivity levels; and

wherein initiating an engagement of the user is dependent on a determined sensitivity level.

10. The system of claim 9 , wherein the plurality of privacy classes is retrieved from a storage.

11. The system of claim 9 , wherein the sensory inputs are collected with respect to the user.

12. The system of claim 9 , wherein the sensory inputs are collected with respect to an entity located within a predetermined distance from the user.

13. The system of claim 12 , wherein the system is further configured to: analyze the sensory inputs for classifying the at least an entity.

14. The system of claim 13 , wherein the system is further configured to: analyze the sensory inputs, the entity's classification, and the privacy rule.

15. The system of claim 9 , wherein the at least a privacy class is determined based on machine learning techniques.

16. The method of claim 1 , wherein:

the sensory inputs comprise one of visual or audio input;

the privacy class indicates a sensitivity level of the user's personal privacy in the social situation; and

the initiating of the engagement includes providing one of audio or visual alerts based on the determined privacy rule.